All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 16,459
- 686
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 8,881–8,904 of 16,459 skills
- Arxiv 2608 19995 The Forward Backward Disconnect State Dynamics CreThe Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation (arXiv: 2608.19995)Votes: 0GitHub stars: 3
- Nerve Brain Fc TokenizationNERVE (Network-Aware Representations of Brain Functional Connectivity via Bilinear Tokenization) - self-supervised learning framework for brain functional connectivity (FC) representation learning. Redefines FC matrix tokenization by partitioning into intra/inter-network connectivity blocks, using structured bilinear factorization for heterogeneous patch sizes. Use when: building brain network ML models, self-supervised fMRI/FC representation learning, masked autoencoder for brain data, brain...Votes: 0GitHub stars: 3
- Neocortex Learning Error Driven PredictiveNeocortex learning framework via error-driven predictive learning using temporal derivatives, corticothalamic circuits, and competitive kinase synaptic plasticity. Activation: neocortex learning, cortical learning, predictive learning, thalamocortical, kinase plasticity, error-driven learning.Votes: 0GitHub stars: 3
- Natural Language AutoencodersMethodology from Anthropic research for converting LLM activations into human-readable natural language text using a reconstruction-based training loop with Activation Verbalizer and Activation Reconstructor.Votes: 0GitHub stars: 3
- Rl Triton Gpu Kernels Credit AssignmentHigh-performance RL credit assignment via Triton kernels.Votes: 0GitHub stars: 3
- Quctrl Bell CompilerCompiler-driven sub-microsecond feedback control stack for trapped-ion quantum experiments. Use when designing quantum control software stacks, compiler pipelines for hardware control, deterministic low-latency feedback systems, DSL transpilation, or real-time quantum hardware synchronization.Votes: 0GitHub stars: 3
- Neurorefiner Multi Agent Neuron SegmentationNeuroRefiner multi-agent 3D neuron segmentation framework.Votes: 0GitHub stars: 3
- Grpo Rl TrainingExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingVotes: 0GitHub stars: 3
- Causalsteward Agentic Causal DiscoveryAn agentic divide-conquer-Combine copilot for causal discovery from high-dimensional data. Leverages massive prior knowledge to address causal identifiability issues in real-world settings where core assumptions are violated. Activation: CausalSteward, causal discovery, agentic copilot, divide-conquer-combine, identifiability, prior knowledge, high-dimensional causal.Votes: 0GitHub stars: 3
- Arxiv 2608 20210 Daedalus 150m A Convolution Attention Hybrid DesigDaedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference (arXiv: 2608.20210)Votes: 0GitHub stars: 3
- Mtc Spiking NetworksMulti-Timescale Conductance Spiking Networks (MTC-SN): A sparse, gradient-trainable SNN framework with rich firing dynamics for enhanced temporal processing. Uses fast/slow/ultra-slow conductances to shape I-V curves, enabling direct BPTT without surrogate gradients. Activation: multi-timescale conductance, MTC-SN, conductance-based SNN, gradient-trainable spiking, temporal regression SNN, neuromorphic regression.Votes: 0GitHub stars: 3
- Mld Quantum DecodingMaximum Likelihood Decoding of QEC codes — unified survey via statistical mechanics, tensor networks, and AIVotes: 0GitHub stars: 3
- Mean Field Molecular Brain BridgeMean-field models bridging molecular to brain scales.Votes: 0GitHub stars: 3
- Lsformer Local Structure Aware Spiking TransformerLSFormer: Local Structure-Aware Spiking Transformer. Replaces global self-attention with dilated local windows and spiking response pooling for energy-efficient SNNs. Keywords: spiking transformer, local attention, SNN, energy-efficient, LSFormer, spiking neural network, self-attention bottleneck, SPooling, LS-SSA, Tiny-ImageNetVotes: 0GitHub stars: 3
- Lottery Bp DecodingLottery BP methodology for scalable quantum error correction decoding. Introduces randomness during belief propagation decoding to improve accuracy by 2-8 orders of magnitude for topological codes (surface, toric, BB codes). Use when: quantum error correction, qLDPC decoding, scalable quantum decoders, belief propagation for quantum codes, syndrome processing, PolyQec architecture, or when building fault-tolerant quantum computing systems requiring real-time decoding.Votes: 0GitHub stars: 3
- Llm Multi Agent Systems Software EngineeringSelect frameworks for LLM multi-agent systems.Votes: 0GitHub stars: 3
- Learning Curve Dataset Size EstimationEmpirical framework to estimate the minimum training-set size needed to reach a target accuracy, via logarithmic learning-curve fitting and a "stability point" metric. Use when planning data collection campaigns, deciding how much labeled data is enough, or extrapolating total data needs from a small pilot study.Votes: 0GitHub stars: 3
- Learnad Alzheimer Interpretable RulesLearnAD: neuro-symbolic method for Alzheimer's disease classification from brain MRI, learning fully interpretable rules combining statistical models and decision logic. Activation: LearnAD, Alzheimer interpretable rules, neuro-symbolic AD classification.Votes: 0GitHub stars: 3
- S3gnn Efficient Graph Mixing"S³GNN (Spectral-Spatial Scalable Graph Neural Network) — efficient global mixing and local message passing for long-range graph learning. Use when building GNNs for tasks with long-range dependencies: (1) graph datasets where oversquashing limits MPNN performance, (2) molecular/biological graph analysis requiring long-range interactions, (3) point cloud or mesh-based physics simulation, (4) knowledge graph QA with multi-hop reasoning.Votes: 0GitHub stars: 3
- Iris Visual Cortex Framework VitIRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers. Provides neuroscience-inspired metrics (RSS, ORS, orientation tuning bandwidth) to quantify how orientation selectivity emerges in ViTs and tracks biologically-grounded features during training. Use when analyzing low-level feature encoding in vision transformers, studying orientation selectivity, or probing representational geometry in transformer models.Votes: 0GitHub stars: 3
- Hybrid Quantum Classical PinnHybrid quantum-classical physics-informed neural network (HQPINN) methodology for solving nonlinear PDEs. Integrates classical NN backbone with parameterized quantum circuits (PQC) to enrich solution representation for problems with sharp gradients, stiff dynamics, and multiscale structure.Votes: 0GitHub stars: 3
- Hybrid Ann Snn Pipeline Local PlasticityNovel hybrid architecture combining pretrained ANN encoder (EfficientNet) with CoLaNET spiking classifier, achieving **99.09% accuracy** on 64-class ImageNet using biologically inspired **local learning rules** without end-to-end gradient propagation. Demonstrates first successful adaptation of powerful pretrained encoders to downstream SNN tasks.Votes: 0GitHub stars: 3
- Hidden Progress Overtraining Sensory CortexHidden progress during overtraining in sensory cortex networks — discovering that overtrained neural networks continue learning useful representations even after apparent performance plateau, with implications for neuroscience and deep learning theory. Activation: overtraining, sensory cortex, hidden progress, learning plateau, groove, deep learning theory, representational change, network training dynamics.Votes: 0GitHub stars: 3
- Mobayes Clinical DecisionModular Bayesian Framework (MoBayes) for separating reasoning from language in clinical decision support. Addresses the architectural limitation of LLMs conflating next-token prediction with probabilistic medical reasoning. Activation: clinical reasoning, medical LLM, Bayesian clinical, decision support, MoBayes, 临床决策.Votes: 0GitHub stars: 3